Audio Source Separation ML Frameworks

Tools and models for isolating individual instruments, vocals, or sound sources from mixed audio signals. Does NOT include speech recognition, speech enhancement without source separation, or general audio processing.

There are 56 audio source separation frameworks tracked. 12 score above 50 (established tier). The highest-rated is pytorch/audio at 64/100 with 2,838 stars. 1 of the top 10 are actively maintained.

Get all 56 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=audio-source-separation&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Framework	Score	Tier	Stars	Language
1	pytorch/audio Data manipulation and transformation for audio signal processing, powered by PyTorch	64	Established	2,838	Python
2	asteroid-team/asteroid The PyTorch-based audio source separation toolkit for researchers	61	Established	2,547	Python
3	deezer/spleeter Deezer source separation library including pretrained models.	56	Established	28,095	Python
4	audeering/opensmile The Munich Open-Source Large-Scale Multimedia Feature Extractor	56	Established	787	C++
5	audeering/opensmile-python Python package for openSMILE	54	Established	307	BitBake
6	markovka17/dla Deep learning for audio processing	54	Established	737	Jupyter Notebook
7	mindspore-lab/mindaudio A toolbox of audio models and algorithms based on MindSpore	51	Established	46	Jupyter Notebook
8	posenhuang/deeplearningsourceseparation Deep Recurrent Neural Networks for Source Separation	51	Established	371	MATLAB
9	f90/Wave-U-Net Implementation of the Wave-U-Net for audio source separation	51	Established	931	Python
10	lars76/swift-f0 Fast and accurate fundamental frequency (F0) detector using convolutional...	51	Established	141	Python
11	MTG/DeepConvSep Deep Convolutional Neural Networks for Musical Source Separation	50	Established	483	Python
12	mikeoliphant/neural-amp-modeler-lv2 Neural Amp Modeler LV2 plugin	50	Established	410	C++
13	xserrat/docker-facebook-demucs Dockerized Facebook Demucs library to make it easy its execution	48	Emerging	187	Makefile
14	drscotthawley/aeiou (ML) audio engineering i/o utils	47	Emerging	54	Jupyter Notebook
15	JusperLee/Dual-Path-RNN-Pytorch Dual-path RNN: efficient long sequence modeling for time-domain...	46	Emerging	464	Python
16	mikeoliphant/NeuralAudio High performance C++ library for neural amp modeler (NAM) and other audio...	46	Emerging	102	C++
17	DamRsn/NeuralNote Audio Plugin for Audio to MIDI transcription using deep learning.	44	Emerging	2,474	C++
18	etzinis/sudo_rm_rf Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf...	42	Emerging	335	Jupyter Notebook
19	demixr/demixr-app Mobile application for music source separation	42	Emerging	63	Dart
20	gemengtju/Tutorial_Separation This repo summarizes the tutorials, datasets, papers, codes and tools for...	42	Emerging	474	MATLAB
21	sk413025/nmf-sound-localizer A modular toolkit for NMF-based sound source localization	42	Emerging	2	Python
22	BingYang-20/SRP-DNN A python implementation of “SRP-DNN: Learning Direct-Path Phase Difference...	42	Emerging	60	Python
23	AidaDSP/aidadsp-lv2 Aida DSP's audio plugins in lv2 format	40	Emerging	37	C++
24	spatialaudio/data-driven-audio-signal-processing-lecture Supplementary materials to the lecture data driven audio signal processing	40	Emerging	31	Jupyter Notebook
25	junyuchen-cjy/DTTNet-Pytorch An official implementation of the ICASSP 2024 paper: Dual-Path TFC-TDF UNet...	39	Emerging	103	Python
26	francescopapaleo/neural-audio-spring-reverb Modelling Spring Reverb with Neural Audio Effects	39	Emerging	62	Python
27	Captain-FLAM/KaraFan The BEST music separation model with help of A.I. ... to my ears ! 👂👂	39	Emerging	147	Python
28	jaron/deep-listening Deep Learning experiments for audio classification	39	Emerging	148	Jupyter Notebook
29	james34602/SpleeterRT Real time monaural source separation base on fully convolutional neural...	38	Emerging	171	C
30	danielfrg/demucs-app Use DEMUCS to split songs into multiple sources	38	Emerging	20	JavaScript
31	emirhanai/Audio-Signal-Processing-Artificial-Intelligence-Project Audio Signal Processing Artificial Intelligence Project	36	Emerging	22	Jupyter Notebook
32	gretatuckute/auditory_brain_dnn Comparison of auditory DNNs and human brain acitivity.	36	Emerging	18	Jupyter Notebook
33	keunwoochoi/dl4mir Deep learning for MIR	36	Emerging	243	Jupyter Notebook
34	01tot10/neural-tape-modeling Neural Modeling of Magnetic Tape Recorders	33	Emerging	27	Python
35	GuitarsAI/TopicsInAudioAndMusicTech Topics in Audio Processing & Music Technology	33	Emerging	34	Jupyter Notebook
36	mayurnewase/looking-to-listen-at-cocktail-party Looking to listen at cocktail party	32	Emerging	36	Jupyter Notebook
37	JaeBinCHA7/DEMUCS-for-Speech-Enhancement We implemented the DEMUCS model for speech enhancement in the time-frequency...	32	Emerging	33	Python
38	Yuan-ManX/SouPyX SouPyX: An Audio Exploration Space.🪐	32	Emerging	42	Python
39	abdozmantar/ComfyUI-DeepExtract DeepExtract is a powerful and efficient tool designed to separate vocals and...	31	Emerging	45	Python
40	huchukato/stemify-audio-splitter 🎵 AI-powered audio separation tool - Split any audio file into vocals,...	30	Emerging	8	TypeScript
41	victor369basu/Audio-Track-Separation In this Repository, We developed an audio track separator in tensorflow that...	30	Emerging	25	Python
42	KinWaiCheuk/demucs_lightning Demucs Lightning: A PyTorch lightning version of Demucs with Hydra and...	30	Emerging	84	Python
43	codehearted/commercialExtractor Tool to detect commercials within recorded audio.	29	Experimental	1	Jupyter Notebook
44	mohammadreza490/music-source-separation-using-Unets This repo explores the concept of blind source separation by training a...	29	Experimental	29	Python
45	chloelavrat/TorchCrepe Implementation of the crepe pitch extractor in PyTorch	24	Experimental	4	Jupyter Notebook
46	cslr/libhypercube-public Freeware DLL binary repository of (audio synthesizer) parameter reduction...	24	Experimental	1	JavaScript
47	Soroushesfn/SSL-in-a-3D-Multi-Surface-Environment Official repository for the research paper "Sound Source Localization in a...	21	Experimental	2	Jupyter Notebook
48	abdozmantar/deepextract DeepExtract Vocal and Sound Separator	20	Experimental	5	Python
49	p-hlp/distributed-source-separation Intelligent Sample Management and Processing	20	Experimental	5	TypeScript
50	ogbabydiesal/RTLEARNER Real-time machine learning system for MaxMSP and Python	19	Experimental	3	Max
51	01tot10/neural-parameter-sampling Sampling the User Controls in Neural Modeling of Audio Devices	18	Experimental	2	—
52	Sony-ASWG/iXML-Extension Sony PlayStation Studios' Audio Standards Working Group - iXML Extension	14	Experimental	17	—
53	juliandeveloper05/Dumu-AI-Bass-Extraction 🎸 AI-powered bass extraction tool. Upload a track, isolate the bass line...	13	Experimental	—	JavaScript
54	ml-dev-world/sonic-source-seperate This repository focuses on algorithms, models, and techniques for isolating...	11	Experimental	—	—
55	sergree/sergree 👋 Мир вам!	11	Experimental	1	—
56	tarolangner/audio_deep_learning Sandbox experiments in deep learning on audio signals	11	Experimental	—	Jupyter Notebook

Comparisons in this category

deeplearningsourceseparation and DeepConvSep (51 vs 50) neural-amp-modeler-lv2 and NeuralAudio (50 vs 46)